Skip to content

Blog · Published · Updated

AI in public offices: case file summaries and the evidence

Short answer

AI in a public office can prepare a summary of the case file and a draft statement of reasons, and the authority still establishes the facts and considers all the evidence, as Poland's Code of Administrative Procedure requires. A good summary keeps conflicting versions of an event and names the source of each fact. At Syntalith the automation costs from €3,000 net, and with 300 cases a month at 20 minutes each it pays back in 1.0 month.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Public administration and AI: statistics 2026

1.0 mo.

payback of a €3,000 automation at 300 cases a month: €3,490 of work on case files today, €538 with checking and the model. Scenario.

Figures checked: 22 October 2026

AI in public offices: the duties stay with the authority

In Poland, the Code of Administrative Procedure (Journal of Laws 2025, item 1691) ties the procedure in Article 7 to a thorough clarification of the facts, and Article 77(1) requires all the evidence to be gathered and considered exhaustively. An AI tool helps with the preparation, and these duties stay with the employee and the authority.

Two versions of an event in one case summary

One document states that an action was carried out, and a later letter from the party contradicts it. The model prepares a short description with the first version. The text reads smoothly, and the employee does not see the discrepancy they should assess. The shorter the summary, the easier it is to lose the opposing evidence, so in the test we count omitted contradictions separately, because they cost the most when a decision is reviewed.

A draft statement of reasons must keep its basis

Article 107(3) of the Code describes the factual reasons as the facts established, the evidence they rest on and the reasons other evidence was not found credible, and the legal reasons as the provisions cited. A draft prepared by AI must therefore show the evidence next to each fact and must not leave out opposing evidence.

What the tool does, and what the employee does
  • Summary

    with references

    Facts with the file and page, contradictions named.

  • Draft

    for assessment

    A proposed statement of reasons with evidence next to each fact.

  • Assessing evidence

    the employee

    Credibility and weight of evidence are the authority's decision.

What AI case file summaries cost and when they pay back

Scenario: 300 cases with files a month
Today
300 cases × 20 min = 100 h (€3,490)
With the system, a person checks the output in 15% of the time
€524
Model, 1 call per case, Claude Sonnet 5.5
€14
Cost of one case
€11.63 today, €1.79 with the system
Saving
€2,952 a month

Payback of €3,000

1.0 month

The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 20,000 input tokens and 1,200 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.

Labour costs in public administration differ from the Eurostat average, so the result is an order of magnitude to check on the office's own cases.

Case files hold the parties' personal data, so the tool runs in an environment the office has approved, with access only for the employees handling the case. According to UODO, the Polish data protection authority (2026), 95.9% of surveyed Polish organisations do not consider themselves ready to roll out AI in line with the GDPR, so we prepare the description of the data flow before the first test on case files.

How to assess the first test

A test on fictional case files
  • Expected results prepared by people who know the procedure
  • Conflicting letters in one case
  • A missing page in the scan of the file
  • Material added after the draft was prepared
  • Whether the employee sees the change and the earlier summary is marked out of date

The first scope is one type of case with a repeatable file layout and a person who knows the expected result. Public bodies can start with a pilot on public instructions, as the article on the AI pilot in a public office describes. For the call, a description of the type of cases and the number of proceedings a month is enough. The document workflow scope is described on document workflow in a public office, and the AI Act duties on the AI Act in a public office.

Worked example · Scenario

How we count the payback: documents in a public office

We run the same count for your office in the free process review.

€1,861

a month for handling 800 documents by hand

Payback: 1.9 mo.

4 minutes per document matched to a case and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: reading a document in our case-file system (about €0.0002) plus matching it to the case and a note on what is missing (Claude Sonnet 5.5, about 2,000 + 300 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026.

See the full calculation →

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

Start with the process that takes the most time each week.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 21, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

AI implementation

Start with the process that takes the most time each week.

The engineer chooses one process with you and calculates how much it costs today. Then we build a free prototype on 20-100 cases that your team has already handled. We write down the goal and the fixed price in the contract.

See AI implementation →
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

Questions

  • Can AI summarise case files in a public office?

    It can prepare a summary and a draft, and the authority establishes the facts and considers all the evidence. The summary must keep conflicting documents and name the source of each fact.

  • What does Poland's Code of Administrative Procedure say about evidence?

    Article 7 ties the procedure to a thorough clarification of the facts, Article 77(1) requires all the evidence to be gathered and considered exhaustively, and Article 107(3) describes the factual reasons with the evidence and why other evidence was not found credible.

  • How much does automating work with case files cost?

    At Syntalith from €3,000 net. With 300 cases a month at 20 minutes each, the payback is 1.0 month. Public bodies can start with a pilot on public instructions.

  • How do you test the tool before use?

    On fictional case files with expected results prepared by people who know the procedure, with conflicting letters, a missing page and material added after the draft was prepared.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
You buy accounts directly from OpenAI or Anthropic and receive an invoice from them. We do not add anything to the license.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.